Dr. Ganguli has been working (and training the next generation) on computational intelligence applications for the mining industry for the last two decades. He is currently using machine learning to create and detect leading indicators for safety incidents. Techniques being used include natural language processing. His team is also using machine learning to detect when sensors first start to stray. Normally, sensor errors are detected only when they are egregious, and after they have resulted in large losses.
In addition to computational intelligence, he acknowledges mining as a truly interdisciplinary industry and recognizes the many opportunities afforded to interdisciplinary teams. His past projects, therefore, included topics such as bacterial remediation of acid mine water, enhancement of mineral flotation processes, recovery of rare earths, training simulator for grinding mills, and effectiveness of coal combustion.
- Machine Learning/ Artifical Intelligence
- Mining Engineering
- Systems Engineering
- Webinar hosted by NITK, India. I was an invited speaker. Talk was about opportunities in US and in mining. Invited Talk/Keynote, Presented, 09/25/2020.
- Mosaic Phosphate, an international mining company, asked me to give a talk on analytics to their leadership during their internal conference. Invited Talk/Keynote, Presented, 08/25/2020.
- Webinar hosted by Anna University, India. I was the sole speaker. Talked about my AI research. Invited Talk/Keynote, Presented, 06/21/2020.
- Presentation to Kennecott Bingham Mine Data Group on my research. Other, Presented, 10/2019.
- Bengali, functional.
- Hindi, functional.
- Telugu, basic.
Besides having work experience in India, Dr. Ganguli has collaborated on technical papers with faculty in Indian universities.
Dr. Ganguli has worked with Erdenet Mining Corporation on mine-mill reconciliation using data mining, sampling and blast movement monitoring. He also led the engineering curriculum design efforts of the American University of Mongolia. In that effort, he worked closely with numerous engineering employers including Oyu Tolgoi and the Government of Mongolia.
- : Process for the Physical Segregation of Minerals (#6675064). Status: Published. Inventors: Jon Yingling, Rajive Ganguli. File date 09/2000; Issue date 01/2004. Country: USA.
- Dynamic Mill Simulation Training Software. A simulator for training mining mill operators to teach them fundamentals of a grinding circuit. Unlike typical simulators in the market, this dynamic simulator is not static. Release Date: 06/2018. Inventors: Conceived by Ganguli, and proposal led by Ganguli. Development led by Ghosh, T., Ganguli, R., etc.
- Ganguli R. (2020) Water in Mongolia: Sources, Uses and Issues, with Special Emphasis on Mining. In: Regmi G., Huettmann F. (eds) Hindu Kush-Himalaya Watersheds Downhill: Landscape Ecology and Conservation Perspectives. Springer, Cham.
- Pimenta, Eduardo de Melo & Ganguli, R. and Pothina, R. (2020). Modification and Enhanced Testing of Data Mining-Based Algorithm to Detect Subtle Errors in Temperature Sensors in Gold Stripping Circuit. Mining, Metallurgy & Exploration.
- Pothina, R. & Ganguli, R. (2020). Detection of Subtle Sensor Errors in Mineral Processing Circuits Using Data-Mining Techniques. Springer.
- Ganguli, R. & Cook, D. R. (2018). Rare earths: A review of the landscape. Cambridge University Press. Vol. 5.
- Srivastava, V, Akdogan, G., Ghosh, T. & Ganguli, R (2018). Dynamic Modeling and Simulation of A Sag For Mill Charge Characterization. Minerals and Metallurgical Processing. Vol. 35.
- Ganguli R., Chieregati A. & Purvee A. (2017). Fundamental error estimation and accounting in the blasthole sampling protocol at a copper mine. (pp. 49-54). Vol. 69. Mining Engineering. Published, 11/01/2017.
- Ganguli R., Purvee A., Sarantsatsral N. & Bat N. (2017). Investigating particle size: Distribution of blasthole samples in an openpit copper mine and its relationship with grade. (pp. 29-33). Vol. 69. Mining Engineering. Published, 02/01/2017.
- Arku, D. & Ganguli, R. (2014). Investigating Utilization Of Aggregated Data: Does It Compromise Information Gleaning. Mining Engineering. Published, 06/2014.
- Aggarwal, S. & Ganguli, R. (2011). Refining Automated Modeling of Operational Data by Identify the Most Important Input Factors. Mining Engineering. Published, 12/2011.
- Dutta S., Bandopadhyay S., Ganguli R. & Misra D. (2011). Critical assessment of machine learning algorithms as estimation techniques for a polymetallic ore deposit. (pp. 899-914). 35th APCOM Symposium - Application of Computers and Operations Research in the Minerals Industry, Proceedings. Published, 12/01/2011.